Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1175
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Ped" or "Pedestrian"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Pedal," indicating a focus on cycling or bicycle-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IELD
    -0.76
    BILITY
    -0.71
     Sheen
    -0.70
    ORGE
    -0.68
     fries
    -0.67
    BuyableInstoreAndOnline
    -0.66
    æ©Ł
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    Reloaded
    -0.63
    ======
    -0.63
    POSITIVE LOGITS
    igree
    1.16
    agog
    1.07
    ricks
    0.94
    iatrics
    0.93
    aling
    0.92
    ersen
    0.92
    iatric
    0.91
    regon
    0.88
    iments
    0.88
    erson
    0.88
    Activations Density 0.009%

    No Known Activations